Skip to content

Use Pod

The inference marketplace. Point any OpenAI- or Anthropic-compatible client at Use Pod and get matched with the best-priced provider that meets your requirements. Pay in USDC, per request.

Use it

Add Use Pod as the base URL of any OpenAI- or Anthropic-compatible client. No SDK changes, no auth changes. Fund a token by card or USDC and pay per request. Quickstart →

Supply it

Run a GPU? Serve open-weight models — or relay your own upstream keys — set your prices, and earn 80% of every settled inference in USDC. Run a provider →

Always-on fallback

Centralized providers (Anthropic, OpenAI, Venice, and more) stay available as a tier-zero fallback. You are never stranded. How routing works →